© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15738
    Prev
    Next
    INDEX
    Explanations

    author names

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    5
    -17.63
    4
    -17.38
    6
    -17.00
    7
    -16.88
    3
    -16.25
    8
    -16.13
     sixty
    -15.94
    ５
    -15.88
     seventeen
    -15.38
    Pi
    -15.25
    POSITIVE LOGITS
    敏
    18.50
    门槛
    17.63
    -decoration
    17.13
    驿
    16.50
    atel
    16.38
    精美
    16.25
    饱和
    15.63
    杂
    15.44
    懔
    15.13
    .addClass
    15.00
    Activations Density 0.523%

    No Known Activations